R Notebook

This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.

Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Ctrl+Shift+Enter. # First part ## data filter and normalization

source("./tianfengRwrappers.R")

冠状动脉

dataset from Nat. Med.

human_coronary_countmatrix <- read.csv("GSE131778_human_coronary_scRNAseq.txt", sep = "\t")
func <- function(s) {
  paste0(strsplit(s, ".", fixed = T)[[1]][2], "_", strsplit(s, ".", fixed = T)[[1]][1])
}
colnames(human_coronary_countmatrix) <- lapply(colnames(human_coronary_countmatrix), func) # 拆分样本

human_coronary <- CreateSeuratObject(counts = human_coronary_countmatrix, 
                                     project = "human_coronary", min.cells = 10, min.features = 300) %>% 
    PercentageFeatureSet(pattern = "^MT-", col.name = "percent.mt") %>%
    subset(subset = nFeature_RNA > 600 & nFeature_RNA < 6000 & nCount_RNA > 1000 &  nCount_RNA < 30000) %>%
    SCTransform(vars.to.regress = "percent.mt", verbose = F) %>% 
    RunPCA() %>% FindNeighbors(dims = 1:20) %>% 
    RunUMAP(dims = 1:20) %>% 
    FindClusters(resolution = 0.1)
rm(human_coronary_countmatrix)

颈动脉斑块 CA dataset1

# 批量读取计数矩阵
# 需要把行名的gene删掉，用vscode修改
count_mats <- list.files("./CA_GSE155512")
count_mats <- count_mats[count_mats != "sampleinfo.txt"]
allList <- lapply(count_mats, function(folder) {
  CreateSeuratObject(
    counts = read.csv(paste0("./CA_GSE155512/", folder), sep = "\t"),
    project = folder, min.cells = 10, min.features = 300
  )
})
# 合并seurat对象
CA_dataset1 <- merge(allList[[1]],
  y = allList[-1], add.cell.ids = count_mats,
  project = "CA_dataset1"
)
rm(allList)

CA_dataset1 <- PercentageFeatureSet(CA_dataset1, pattern = "^MT-", col.name = "percent.mt") %>%
    subset(subset = nFeature_RNA > 600 & nFeature_RNA < 6000 & nCount_RNA > 1000 &  nCount_RNA < 30000) %>%
    SCTransform(vars.to.regress = "percent.mt", verbose = F) %>% 
    RunPCA() %>% FindNeighbors(dims = 1:20) %>% 
    RunUMAP(dims = 1:20) %>% 
    FindClusters(resolution = 0.1)

颈动脉斑块 CA dataset2

CA_dataset2 <- CreateSeuratObject(Read10X("./CA_GSE159677/"), names.field = 2, names.delim = "-",
                                   project = "CA_dataset2", min.cells = 10, min.features = 300) %>% 
  PercentageFeatureSet(pattern = "^MT-", col.name = "percent.mt") %>%
  subset(subset = nFeature_RNA > 600 & nFeature_RNA < 6000 & nCount_RNA > 1000 &  nCount_RNA < 30000) %>%
  SCTransform(vars.to.regress = "percent.mt", verbose = F) %>% 
  RunPCA() %>% FindNeighbors(dims = 1:20) %>% 
  RunUMAP(dims = 1:20) %>% 
  FindClusters(resolution = 0.1)

添加metadata samples存储完整信息，conditions按区域分，groups按病例分

Idents(human_coronary) <- human_coronary$orig.ident
Idents(human_coronary) <- c("1","1","2","2","3","3","4","4")
human_coronary$samples <- Idents(human_coronary)
Idents(human_coronary) <- human_coronary$seurat_clusters

Idents(CA_dataset2) <- CA_dataset2$orig.ident
CA_dataset2 <- RenameIdents(CA_dataset2,'1' = 'AC_1','2' = 'PA_1','3' = 'AC_2','4' = 'PA_2','5' = 'AC_3','6' = 'PA_3')
UMAPPlot(CA_dataset2)

CA_dataset2$sample <- Idents(CA_dataset2)
CA_dataset2 <- RenameIdents(CA_dataset2,'AC_1' = 'AC','PA_1' = 'PA','AC_2'= 'AC','PA_2'= 'PA','AC_3'= 'AC','PA_3'= 'PA')
CA_dataset2$conditions <- Idents(CA_dataset2)
Idents(CA_dataset2) <- CA_dataset2$orig.ident
CA_dataset2 <- RenameIdents(CA_dataset2, '1' = 'sp_1','2' = 'sp_1','3' = 'sp_2','4' = 'sp_2','5' = 'sp_3','6' = 'sp_3')
CA_dataset2$groups <- Idents(CA_dataset2)
Idents(CA_dataset2) <- CA_dataset2$seurat_clusters

保存结果

saveRDS(human_coronary,"human_coronary.rds")
saveRDS(CA_dataset1,"CA_dataset1.rds")
saveRDS(CA_dataset2,"CA_dataset2.rds") #已经经过分组处理了

Idents(CA_dataset2) <- CA_dataset2$conditions
AC <- subset(CA_dataset2, idents = "AC")
PA <- subset(CA_dataset2, idents = "PA")

AC <- AC %>% RunPCA() %>% FindNeighbors(dims = 1:20) %>% 
  RunUMAP(dims = 1:20) %>% 
  FindClusters(resolution = 0.1)
PA <- PA %>% RunPCA() %>% FindNeighbors(dims = 1:20) %>% 
  RunUMAP(dims = 1:20,seed.use = 20) %>% 
  FindClusters(resolution = 0.1)

AC <- AC %>% RunUMAP(dims = 1:20,seed.use = 20) %>% 
  FindClusters(resolution = 0.1)

SMC <- SMC %>% FindNeighbors(dims = 1:20) %>% FindClusters(resolution = 0.2)

Computing nearest neighbor graph
Computing SNN

Modularity Optimizer version 1.3.0 by Ludo Waltman and Nees Jan van Eck

Number of nodes: 3057
Number of edges: 98364

Running Louvain algorithm...

0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|

Maximum modularity in 10 random starts: 0.9273
Number of communities: 5
Elapsed time: 0 seconds